Abstract | ||
---|---|---|
The evaluation of systems that parse natural language, on the basis of a score like bracketing accuracy or sentence accuracy, on an unseen text is becoming an important issue in grammar building and parsing. The statistical induction of grammars and the statistical training of (hand written) grammars are ways to attain or improve a score, but a stochastic grammar does not reflect the often stereotypical use of words depending on their semantical categories, often referred to as selectional restrictions or semantical patterns. |
Year | DOI | Venue |
---|---|---|
1995 | 10.1007/3-540-60925-3_45 | Connectionist, Statistical, and Symbolic Approaches to Learning for Natural Language Processing |
Keywords | Field | DocType |
training stochastic grammar,semantical category,natural language | Tree-adjoining grammar,Context-sensitive grammar,L-attributed grammar,Computer science,Phrase structure grammar,Indexed grammar,Grammar,Natural language processing,Artificial intelligence,Parsing,Stochastic grammar | Conference |
ISBN | Citations | PageRank |
3-540-60925-3 | 1 | 0.42 |
References | Authors | |
17 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wide R. Hogenhout | 1 | 8 | 2.31 |
yuji matsumoto | 2 | 3008 | 300.05 |